compressa-ai
/

Saiga-Llama-3-8B-AdaQRound

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

Vasily Alexeev commited on Apr 27

Commit

cb827dc

•

1 Parent(s): 4d5ac10

fix model path in code example

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -176,7 +176,7 @@ Quantized with AdaQRound which is a combination of [AdaRound](https://arxiv.org/
 ### Inference
 ```python
-model_path = "compressa-ai/Saiga-Llama-3-8B-OmniQuant"
 model = load_model(model_path).cuda()
 tokenizer = AutoTokenizer.from_pretrained(

 ### Inference
 ```python
+model_path = "compressa-ai/Saiga-Llama-3-8B-AdaQRound"
 model = load_model(model_path).cuda()
 tokenizer = AutoTokenizer.from_pretrained(